Official models are just like other models on Replicate, but with a few extra benefits:
Recommended Models
Recommended Models

openai/gpt-5.6-lunaOpenAI's GPT-5.6 cost-optimized tier, built for fast, high-volume, latency-sensitive workloads.
Updated 8 hours ago
4 runs

openai/gpt-5.6-terraOpenAI's GPT-5.6 balanced tier, tuned for everyday production work at roughly half the cost of the flagship.
Updated 8 hours ago
7 runs

openai/gpt-5.6-solOpenAI's GPT-5.6 flagship tier, built for complex professional work, coding, and deep multi-step reasoning.
Updated 8 hours ago
133 runs

openai/gpt-image-2OpenAI's state-of-the-art image generation model. Create and edit images from text with strong instruction following, sharp text rendering, and detailed editing.
Updated 1 day, 9 hours ago
13.1M runs

Google's fastest image generation model — the lightweight, low-cost version of Nano Banana 2, for rapid creation and editing
Updated 4 days, 4 hours ago
21.8K runs

prunaai/p-image-try-onVirtual try-on. Put one or more garments onto a person photo while keeping their face, pose, and body.
Updated 1 week ago
9.1K runs

Qwen3.7-Plus is Alibaba's cost-effective multimodal model with vision-language understanding, a 1 million token context window, and strong agentic coding and tool use.
Updated 2 weeks ago
8.4K runs
VEED Fabric 1.0 is an image-to-video API that turns any image into a talking video
Updated 2 weeks ago
44.3K runs
bytedance/seedance-2.0-miniA lower-cost variant of Seedance 2.0 for high-volume video generation with multimodal inputs and native audio.
Updated 2 weeks, 1 day ago
10K runs

bytedance/seedance-2.0ByteDance's multimodal video generation model with native audio, multimodal reference inputs, and intelligent duration control.
Updated 2 weeks, 2 days ago
1.1M runs
Alibaba's Happy Horse 1.1 generates videos from text, animates a single image, or builds a video from multiple reference images. Supports 720p and 1080p, 3-15 second durations, and five aspect ratios.
Updated 2 weeks, 3 days ago
4.4K runs

prunaai/p-image-editA sub 1 second 0.01$ multi-image editing model built for production use cases. For image generation, check out p-image here: https://replicate.com/prunaai/p-image
Updated 2 weeks, 3 days ago
35.7M runs

Google's fast multimodal model with frontier reasoning across agents, coding, and long-context tasks
Updated 2 weeks, 6 days ago
153K runs

Google's fast, expressive text-to-speech model with 30 voices and 70+ language support
Updated 2 weeks, 6 days ago
265.1K runs

Google's most intelligent model, with improved reasoning and a new medium thinking level
Updated 2 weeks, 6 days ago
1.3M runs

Google's most advanced reasoning Gemini model
Updated 2 weeks, 6 days ago
1.3M runs

Google's most intelligent model built for speed with frontier intelligence, superior search, and grounding
Updated 2 weeks, 6 days ago
5.3M runs

Google’s hybrid “thinking” AI model optimized for speed and cost-efficiency
Updated 2 weeks, 6 days ago
8.9M runs

prunaai/p-imageA sub 1 second text-to-image model built for production use cases.
Updated 2 weeks, 6 days ago
13.4M runs

Google's fast image generation model with conversational editing, multi-image fusion, and character consistency
Updated 2 weeks, 6 days ago
14.1M runs
Generate full-length songs up to 3 minutes from text prompts or images with Lyria 3 Pro, Google's most capable music generation model
Updated 2 weeks, 6 days ago
22.3K runs

Generate 30-second music clips from text prompts or images with Lyria 3, Google's music generation model
Updated 2 weeks, 6 days ago
260.6K runs
Extend videos with xAI's Grok Imagine Video model. Provide a source video and describe what happens next.
Updated 3 weeks ago
5.6K runs
Generate videos using xAI's Grok Imagine Video model
Updated 3 weeks ago
1.3M runs
Image-to-video with synchronized audio using xAI's Grok Imagine Video 1.5 preview model
Updated 3 weeks ago
110.8K runs
Generate videos guided by reference images using xAI's Grok Imagine Video model
Updated 3 weeks ago
61.7K runs

prunaai/p-image-upscaleFastest image upscaler in the world (<1s) supporting outputs up to 128 MP.
Updated 3 weeks, 3 days ago
548.4K runs

Top-quality agentic image model with multi-step reasoning, candidate scoring, and adjustable thinking effort
Updated 4 weeks ago
828 runs

Speed-optimized variant of Riverflow 2.5 for production and latency-sensitive workflows
Updated 4 weeks ago
988 runs

luma/ray-3.2Luma's reasoning video model. Generates cinematic 5s or 10s video from text or images, with native HDR and EXR export for professional production pipelines.
Updated 4 weeks, 1 day ago
1.9K runs

Claude Fable 5 from Anthropic: the next generation of intelligence for the hardest knowledge work and coding problems.
Updated 1 month ago
3.4K runs

Upscale images 2x or 4x times
Updated 1 month ago
759.4K runs

ideogram-ai/ideogram-v4-balancedBalance speed, quality and cost. Ideogram v4 creates images with stunning realism, creative designs, and consistent styles
Updated 1 month ago
5.2K runs

ideogram-ai/ideogram-v4-qualityThe highest quality Ideogram v4 model. v4 creates images with stunning realism, creative designs, and consistent styles
Updated 1 month ago
12.9K runs
runwayml/aleph-2Edit one frame to update an entire video. Aleph 2.0 is Runway's in-context video editor: longer clips (up to 30s), multi-shot edits, and image-level precision via keyframe references.
Updated 1 month, 1 week ago
1.3K runs

bytedance/seedream-4.5Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge
Updated 1 month, 1 week ago
34.4M runs
prunaai/p-video-avatarp-video-avatar is the fastest and cheapest avatar/lipsync video model on the market.
Updated 1 month, 1 week ago
91K runs

Krea's flagship foundation image model. Larger and more flexible than Krea 2 Medium, with particular strength in photorealism and expressive artistic styles.
Updated 1 month, 1 week ago
2.4K runs

Foundation image model from Krea, tuned for expressive illustration, anime, and painterly styles. Fast and consistent across artistic directions.
Updated 1 month, 1 week ago
14K runs
prunaai/p-video-animatep-video-animate animates a reference image with the motion and audio of a source video. Optimized for speed and cost — 5.24s per 1s of video.
Updated 1 month, 1 week ago
6.8K runs
prunaai/p-video-replacep-video-replace swaps the person in a video with one from a reference image, keeping motion, timing, camera, and scene exactly as they were. 3.58s per 1s of video generated.
Updated 1 month, 1 week ago
6.8K runs

Claude Sonnet 4.6 from Anthropic: a full upgrade to coding, computer use, long-context reasoning, agent planning, knowledge work, and design, with a 1 million token context window in beta.
Updated 1 month, 1 week ago
23.3K runs

ibm-granite/granite-vision-4.1-4bGranite Vision 4.1 4B is a vision-language model (VLM) that delivers frontier-level performance on structured document extraction tasks — chart extraction, table extraction, and semantic key-value pair extraction — in a compact 4B parameter footprint
Updated 1 month, 1 week ago
15K runs

ibm-granite/granite-speech-4.1-2bGranite Speech 4.1 2B is a compact and efficient speech-language model, specifically designed for multilingual automatic speech recognition (ASR) and bidirectional automatic speech translation (AST) for English, French, German, Spanish, Portuguese and Jap
Updated 1 month, 1 week ago
1.9K runs

ibm-granite/granite-4.1-8bGranite-4.1-8B is a 8B parameter long-context instruct model finetuned from Granite-4.1-8B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
Updated 1 month, 1 week ago
26.6K runs

bytedance/seedance-1-liteA video generation model that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 720p resolution
Updated 1 month, 2 weeks ago
3.6M runs
bytedance/video-upscalerUpscale and enhance video up to 4K at 60fps, with scene-aware presets for AI-generated content, short dramas, UGC, and film restoration.
Updated 1 month, 2 weeks ago
6.7K runs

Create realistic talking avatar videos from text with HeyGen's Avatar V engine — the newest, highest-quality avatar engine with cross-reference-driven animation.
Updated 1 month, 3 weeks ago
251 runs
recraft-ai/recraft-v4.1-svgGenerate production-ready SVG vector images from text prompts. Recraft V4.1's design taste applied to vector output — clean geometry, structured layers, and editable paths.
Updated 1 month, 4 weeks ago
5.2K runs

recraft-ai/recraft-v4.1Recraft's latest image generation model, built around design taste. Strong prompt accuracy, art-directed composition, and integrated text rendering. Fast and cost-efficient at standard resolution.
Updated 1 month, 4 weeks ago
41.2K runs

recraft-ai/recraft-v4.1-proRecraft's latest image generation model at ~2048px resolution. Same design taste and prompt accuracy as V4.1, with higher resolution for print-ready and large-scale work.
Updated 1 month, 4 weeks ago
19K runs

recraft-ai/recraft-v4.1-utility-proA faster, lighter Recraft image generation model at ~2048px resolution, optimized for high-volume production. Design taste and prompt accuracy at high resolution with better throughput.
Updated 1 month, 4 weeks ago
1.5K runs

recraft-ai/recraft-v4.1-utilityA faster, lighter Recraft image generation model optimized for high-volume and production pipelines. Same design taste as V4.1, built for speed and throughput.
Updated 1 month, 4 weeks ago
24.2K runs
recraft-ai/recraft-v4.1-pro-svgGenerate detailed SVG vector graphics from text prompts. Recraft V4.1 Pro's design taste with more geometric detail and finer paths — clean layers, editable output, and scalable to any size.
Updated 1 month, 4 weeks ago
1.7K runs

prunaai/z-image-turboZ-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
Updated 1 month, 4 weeks ago
48.1M runs

A unified Text-to-Speech demo featuring three powerful modes: Voice, Clone and Design
Updated 2 months ago
964.4K runs

xAI's higher-quality image model with sharper details, better text rendering, and 2k output
Updated 2 months ago
287.6K runs
Studio-grade lipsync in minutes, not weeks
Updated 2 months ago
46.6K runs

Transcribe speech with ElevenLabs Scribe v2. 90+ languages, word-level timestamps, speaker diarization for up to 32 speakers, audio event tagging, and keyterm biasing. Files up to 3 GB and 10 hours.
Updated 2 months ago
42.9K runs

meta/llama-4-maverick-instructA 17 billion parameter model with 128 experts
Updated 2 months ago
5.2M runs

openai/gpt-oss-20b20b open-weight language model from OpenAI
Updated 2 months ago
641.5K runs

openai/gpt-oss-120b120b open-weight language model from OpenAI
Updated 2 months ago
277.2K runs

meta/llama-guard-4-12bUpdated 2 months ago
241.1K runs

Kimi K2 Thinking is the latest, most capable version of an open-source thinking model.
Updated 2 months ago
4.9K runs

meta/llama-4-scout-instructA 17 billion parameter model with 16 experts
Updated 2 months ago
3.7M runs

deepseek-ai/deepseek-r1A reasoning model trained with reinforcement learning, on par with OpenAI o1
Updated 2 months ago
2.3M runs

deepseek-ai/deepseek-v3DeepSeek-V3-0324 is the leading non-reasoning model, a milestone for open source
Updated 2 months ago
5.3M runs

deepseek-ai/deepseek-v3.1Latest hybrid thinking model from Deepseek
Updated 2 months ago
502.2K runs

Updated Qwen3 model for instruction following
Updated 2 months ago
1.1M runs

Most expressive text-to-speech model from Inworld, with natural-language steering, real-time latency, and multilingual support across 100+ languages.
Updated 2 months ago
26.9K runs

FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.
Updated 2 months ago
21.1M runs

Max-quality image generation and editing with support for ten reference images
Updated 2 months ago
431.9K runs

philz1337x/clarity-pro-upscalerThe first creative upscaler which keeps identity. Stunning photorealistic results, realistic skin, and full creative control.
Updated 2 months, 1 week ago
18K runs

Convert text to natural-sounding speech with xAI's Grok TTS. 5 voices, 20 languages, expressive speech tags, and high-fidelity MP3 / WAV / telephony audio output.
Updated 2 months, 1 week ago
670.6K runs

Transcribe audio to text with xAI's Grok. Handles 25 languages, word-level timestamps, speaker diarization, multichannel audio, and files up to 500 MB.
Updated 2 months, 1 week ago
5K runs
Alibaba's Happy Horse 1.0 generates videos from text prompts or animates a single image into video. Supports 720p and 1080p, 3-15 second durations, and five aspect ratios.
Updated 2 months, 2 weeks ago
27.1K runs
prunaai/p-videoFast video generation with built-in draft mode for rapid creative iteration. Text-to-video, image-to-video, and audio-to-video in a single endpoint.
Updated 2 months, 2 weeks ago
2M runs

ibm-granite/granite-embedding-small-english-r2Granite-embedding-small-english-r2 is a 47M parameter dense biencoder embedding model from the Granite Embeddings collection that can be used to generate high quality text embeddings.
Updated 2 months, 2 weeks ago
187 runs
Kling Video 3.0 Omni: Unified multimodal video generation with reference images, video editing, native audio, and multi-shot control
Updated 2 months, 2 weeks ago
711.5K runs
Kling Video 3.0: Generate cinematic videos up to 15 seconds with multi-shot control, native audio, and improved consistency
Updated 2 months, 2 weeks ago
361.4K runs

Moonshot AI's frontier open model, built for long-horizon coding, agent swarms, and autonomous software engineering. 1 trillion parameters, 262k context window, vision and tool use.
Updated 2 months, 2 weeks ago
52.5K runs
PixVerse's flagship video generation model. Generate cinematic videos with synchronized audio, multi-shot sequences, and precise camera control.
Updated 2 months, 2 weeks ago
91.6K runs
bytedance/seedance-2.0-fastA faster variant of Seedance 2.0 for quicker video generation with multimodal inputs and native audio.
Updated 2 months, 2 weeks ago
553.5K runs

Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Optimized for high-fidelity applications like voiceovers and audiobooks.
Updated 2 months, 2 weeks ago
2.6M runs

MiniMax Speech 2.6 HD delivers studio-quality multilingual text-to-audio on Replicate with nuanced prosody, subtitle export, and premium voices
Updated 2 months, 2 weeks ago
193K runs

Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Designed for real-time applications with low latency
Updated 2 months, 2 weeks ago
12.7M runs

Minimax Speech 2.8 HD focuses on high-fidelity audio generation with features like studio-grade quality, flexible emotion control, multilingual support, and voice cloning capabilities
Updated 2 months, 2 weeks ago
150.1K runs

Low‑latency MiniMax Speech 2.6 Turbo brings multilingual, emotional text-to-speech to Replicate with 300+ voices and real-time friendly pricing
Updated 2 months, 2 weeks ago
1.1M runs

Minimax Speech 2.8 Turbo: Turn text into natural, expressive speech with voice cloning, emotion control, and support for 40+ languages
Updated 2 months, 2 weeks ago
365.5K runs
Enables precise control of character actions and expressions from a reference image.
Updated 2 months, 3 weeks ago
1.1M runs

Google's latest image generation model in Gemini 2.5
Updated 2 months, 3 weeks ago
1.3M runs

Generate videos from reference images or clips while preserving subject identity using Alibaba's Wan 2.7 reference-to-video model
Updated 2 months, 3 weeks ago
3.6K runs
Edit videos with natural language instructions using Alibaba's Wan 2.7 VideoEdit model
Updated 2 months, 3 weeks ago
13.7K runs

Generate videos from images, with support for first-and-last-frame control, clip continuation, and audio synchronization using Alibaba's Wan 2.7 model
Updated 2 months, 3 weeks ago
65K runs

Reimagine any song in a different style — change voice, instruments, genre, and arrangement while keeping the original melody
Updated 2 months, 3 weeks ago
3.7K runs

Generate 3D character animation data from a text prompt
Updated 2 months, 3 weeks ago
186 runs

Generate 3D character animation data from a text prompt
Updated 2 months, 3 weeks ago
64 runs

Rig any 3D bipedal character mesh
Updated 2 months, 3 weeks ago
194 runs

Use this fast version of Imagen 4 when speed and cost are more important than quality
Updated 2 months, 3 weeks ago
5.8M runs
Turn a text prompt into a complete, polished video with AI-generated script, avatar presenter, voiceover, visuals, and editing.
Updated 2 months, 3 weeks ago
1K runs
Create avatar videos with realistic humans, animals, cartoons, or stylized characters
Updated 2 months, 3 weeks ago
22.4K runs

Fast lip-sync: replace or dub audio on any video with quick audio-driven lip sync
Updated 2 months, 3 weeks ago
968 runs
Translate videos into over 150 languages
Updated 2 months, 3 weeks ago
9.7K runs

High-accuracy lip-sync: replace or dub audio on any video with avatar-inference lip sync
Updated 2 months, 3 weeks ago
4K runs
Create realistic talking avatar videos from text with HeyGen's Avatar IV engine
Updated 2 months, 3 weeks ago
642 runs

Anthropic's most capable model with a step-change improvement in agentic coding, better vision, and stronger multi-step reasoning
Updated 2 months, 3 weeks ago
148.6K runs

Highest-quality realtime text-to-speech with <200ms latency, emotion control, and 15-language support
Updated 2 months, 3 weeks ago
157.4K runs

Ultra-fast, cost-efficient realtime text-to-speech with ~120ms latency and 15-language support
Updated 2 months, 3 weeks ago
100.6K runs

Use this ultra version of Imagen 4 when quality matters more than speed and cost
Updated 2 months, 3 weeks ago
1.7M runs

Professional inpainting and outpainting model with state-of-the-art performance. Edit or extend images with natural, seamless results.
Updated 2 months, 3 weeks ago
4.1M runs
High-fidelity video generation with text-to-video, image-to-video, and start-end-to-video modes. Up to 16 seconds at 1080p with synchronized audio.
Updated 2 months, 3 weeks ago
3.3K runs
Fast video generation with text-to-video, image-to-video, and start-end-to-video modes. Up to 16 seconds at 1080p with synchronized audio.
Updated 2 months, 3 weeks ago
2.1K runs
Kling 2.5 Turbo Pro: Unlock pro-level text-to-video and image-to-video creation with smooth motion, cinematic depth, and remarkable prompt adherence.
Updated 2 months, 4 weeks ago
2.8M runs

luma/reframe-imageChange the aspect ratio of any photo using AI (not cropping)
Updated 2 months, 4 weeks ago
315.6K runs

Generate full-length songs or instrumentals from a text prompt, with optional auto-generated lyrics
Updated 3 months ago
18.2K runs
Edit and transform videos with text prompts and reference images. Style transfers, object replacement, character transformation, and more.
Updated 3 months ago
192 runs

Generate full-length songs with vocals, lyrics, and rich instrumentation from a text prompt
Updated 3 months ago
10.3K runs

prunaai/hidream-l1-fastThis is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!
Updated 3 months ago
8.4M runs

ideogram-ai/layerizeTake a flat graphic, remove text, and get structured text layers back for editing and recomposing
Updated 3 months ago
6.2K runs
Generate videos with audio from text prompts using Alibaba's Wan 2.7 model. 1080p, up to 15 seconds, with audio synchronization.
Updated 3 months, 1 week ago
6.2K runs

Generate and edit images with Alibaba's Wan 2.7
Updated 3 months, 1 week ago
113.2K runs

Generate and edit high-quality images with Alibaba's Wan 2.7 Pro with 4K output, thinking mode, text-to-image, multi-image editing, and image set generation
Updated 3 months, 1 week ago
148.6K runs

Google's cost-efficient video generation model with native audio, optimized for high-volume applications
Updated 3 months, 1 week ago
60.4K runs
New and improved version of Veo 3 Fast, with higher-fidelity video, context-aware audio and last frame support
Updated 3 months, 2 weeks ago
732.2K runs
New and improved version of Veo 3, with higher-fidelity video, context-aware audio, reference image and last frame support
Updated 3 months, 2 weeks ago
552.6K runs

High-quality image generation and editing with support for eight reference images
Updated 3 months, 2 weeks ago
9.1M runs

The highest fidelity image model from Black Forest Labs
Updated 3 months, 3 weeks ago
3.6M runs

recraft-ai/recraft-remove-backgroundAutomated background removal for images. Tuned for AI-generated content, product photos, portraits, and design workflows
Updated 3 months, 4 weeks ago
1.3M runs

recraft-ai/recraft-creative-upscaleCreative Upscale focuses on enhancing details and refining complex elements in the image. It doesn’t just increase resolution but adds depth by improving textures, fine details, and facial features.
Updated 3 months, 4 weeks ago
17K runs

recraft-ai/recraft-vectorizeConvert raster images to high-quality SVG format with precision and clean vector paths, perfect for logos, icons, and scalable graphics.
Updated 3 months, 4 weeks ago
773K runs

recraft-ai/recraft-crisp-upscaleDesigned to make images sharper and cleaner, Crisp Upscale increases overall quality, making visuals suitable for web use or print-ready materials.
Updated 3 months, 4 weeks ago
4.5M runs
lightricks/ltx-2-proDelivers high visual fidelity with fast turnaround. Great for daily content creation, marketing teams, and iterative creative workflows.
Updated 4 months ago
23.2K runs
lightricks/ltx-2-fastIdeal for rapid ideation and mobile workflows. Perfect for creators who need instant feedback, real-time previews, or high-throughput content.
Updated 4 months ago
83.8K runs
lightricks/ltx-2.3-proHigh-fidelity video generation with portrait support, audio-to-video, retake, and extend. Text, image, and audio-driven creation up to 4K at 50 FPS.
Updated 4 months ago
49.4K runs

openai/gpt-5.4OpenAI's most capable frontier model for complex professional work, coding, and multi-step reasoning.
Updated 4 months ago
211.9K runs
lightricks/ltx-2.3-fastLightning-fast video generation with portrait support, camera controls, and synchronized audio. Up to 20 seconds at 1080p, 4K at 50 FPS.
Updated 4 months ago
32.2K runs
Kling 3.0 motion control: transfer motion from a reference video to any character image with improved consistency and quality.
Updated 4 months ago
465.3K runs

The pro version of Qwen Image 2 from Alibaba's Qwen team. Enhanced text rendering, realism, and semantic adherence for high-quality image generation and editing.
Updated 4 months ago
50.6K runs

A next-generation image generation and editing model from Alibaba's Qwen team. Supports text-to-image and image editing with strong text rendering, especially for Chinese.
Updated 4 months ago
53.3K runs

Google's state of the art image generation and editing model 🍌🍌
Updated 4 months, 2 weeks ago
32.1M runs

ibm-granite/granite-4.0-h-smallGranite-4.0-H-Small is a 32B parameter long-context instruct model finetuned from Granite-4.0-H-Small-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
Updated 4 months, 2 weeks ago
232.8K runs

bytedance/seedream-5-liteSeedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep domain knowledge
Updated 4 months, 2 weeks ago
3M runs
recraft-ai/recraft-v4-pro-svgGenerate detailed SVG vector graphics from text prompts. Recraft V4 Pro's design taste with more geometric detail and finer paths — clean layers, editable output, and scalable to any size.
Updated 4 months, 3 weeks ago
9.5K runs

recraft-ai/recraft-v4-proRecraft's latest image generation model at ~2048px resolution. Same design taste and prompt accuracy as V4, with higher resolution for print-ready and large-scale work.
Updated 4 months, 3 weeks ago
19.1K runs

recraft-ai/recraft-v4Recraft's latest image generation model, built around design taste. Strong prompt accuracy, art-directed composition, and integrated text rendering. Fast and cost-efficient at standard resolution.
Updated 4 months, 3 weeks ago
939.1K runs
recraft-ai/recraft-v4-svgGenerate production-ready SVG vector images from text prompts. Recraft V4's design taste applied to vector output — clean geometry, structured layers, and editable paths.
Updated 4 months, 3 weeks ago
42.4K runs

Bria Expand expands images beyond their borders in high quality. Resizing the image by generating new pixels to expand to the desired aspect ratio. Trained exclusively on licensed data for safe and risk-free commercial use
Updated 4 months, 3 weeks ago
394.7K runs
runwayml/gen-4.5State-of-the-art video motion quality, prompt adherence and visual fidelity
Updated 4 months, 3 weeks ago
285.4K runs

prunaai/p-image-loraUse trained LoRAs from the https://replicate.com/prunaai/p-image-trainer. Find or contribute LoRAs here https://huggingface.co/collections/PrunaAI/p-image-loras
Updated 4 months, 3 weeks ago
124K runs
Modify an existing video through natural-language commands, changing subjects, environments, and visual style while preserving the original motion and timing.
Updated 4 months, 3 weeks ago
14.9K runs

Google's Imagen 4 flagship model
Updated 4 months, 3 weeks ago
8.1M runs

Google's highest quality text-to-image model, capable of generating images with detail, rich lighting and beauty
Updated 4 months, 3 weeks ago
2.2M runs

A faster and cheaper Imagen 3 model, for when price or speed are more important than final image quality
Updated 4 months, 3 weeks ago
625.8K runs

SOTA image model from xAI
Updated 4 months, 3 weeks ago
3.1M runs

prunaai/p-image-trainerFast LoRA trainer for p-image, a super fast text-to-image model developed by Pruna AI. Use LoRAs here: https://replicate.com/prunaai/p-image-lora. Find or contribute LoRAs here: https://huggingface.co/collections/PrunaAI/p-image
Updated 4 months, 3 weeks ago
295 runs

prunaai/p-image-edit-loraUse trained LoRAs from the https://replicate.com/prunaai/p-image-edit-trainer. Find or contribute LoRAs here: https://huggingface.co/collections/PrunaAI/p-image-edit-loras.
Updated 4 months, 3 weeks ago
272.9K runs
Automatically remove backgrounds from videos -perfect for creating clean, professional content without a green screen.
Updated 4 months, 4 weeks ago
2.3K runs
Upscale videos up to 8K output resolution. Trained on fully licensed and commercially safe data.
Updated 4 months, 4 weeks ago
287 runs
tencent/hunyuan-3d-3.13D models with texture fidelity and geometry precision
Updated 4 months, 4 weeks ago
73.7K runs
bytedance/dreamactor-m2.0Animate any character, humans, cartoons, animals, even non-humans, from a single image + driving video
Updated 5 months ago
21.8K runs
A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency
Updated 5 months ago
730 runs

FIBO-Edit brings the power of structured prompt generation to image editing
Updated 5 months ago
7.8K runs

topazlabs/dust-and-scratch-v2Remove dust and scratches from old photos
Updated 5 months ago
2K runs

topazlabs/image-colorizationImage colorization model from Topaz Labs
Updated 5 months ago
1.8K runs

Google's latest image editing model in Gemini 2.5
Updated 5 months ago
113.3M runs

Bria Increase resolution upscales the resolution of any image. It increases resolution using a dedicated upscaling method that preserves the original image content without regeneration.
Updated 5 months ago
131K runs

SOTA Open source model trained on licensed data, transforming intent into structured control for precise, high-quality AI image generation in enterprise and agentic workflows.
Updated 5 months ago
13.8K runs

Bria Background Generation allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use
Updated 5 months ago
73.2K runs

Commercial-ready, trained entirely on licensed data, text-to-image model. With only 4B parameters provides exceptional aesthetics and text rendering. Evaluated to be on par to other leading models in the market
Updated 5 months ago
171.2K runs

SOTA Object removal, enables precise removal of unwanted objects from images while maintaining high-quality outputs. Trained exclusively on licensed data for safe and risk-free commercial use
Updated 5 months ago
509.6K runs

Bria GenFill enables high-quality object addition or visual transformation. Trained exclusively on licensed data for safe and risk-free commercial use.
Updated 5 months ago
22K runs

Bria AI's remove background model
Updated 5 months ago
2.3M runs

Anthropic's most intelligent model with state-of-the-art coding, reasoning, and agentic capabilities
Updated 5 months ago
180.6K runs
Image-to-video generation with optional audio, multi-shot narrative support, and faster inference
Updated 5 months ago
80.7K runs

Agentic image model optimized for robust, high-precision generations supporting font control
Updated 5 months ago
21.7K runs

Agentic image model optimized for high-quality, fast generations supporting font control
Updated 5 months ago
10K runs

Render product images with 100% accuracy and environmental blending
Updated 5 months, 1 week ago
466 runs
Latest video model from Pixverse with astonishing physics
Updated 5 months, 1 week ago
31K runs
Use Wan 2.2 Animate to replace a character in a video scene
Updated 5 months, 1 week ago
49.2K runs

A version of FLUX.2 [klein] 4B-base that supports fast fine-tuned lora inference
Updated 5 months, 1 week ago
1.4K runs

A version of FLUX.2 [klein] 9B-base that supports fast fine-tuned lora inference
Updated 5 months, 1 week ago
19.9K runs
lightricks/audio-to-videoUse audio input with an image or prompt to generate videos
Updated 5 months, 1 week ago
2K runs

Moonshot AI's latest open model. It unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model
Updated 5 months, 1 week ago
53.3K runs

openai/gpt-4oOpenAI's high-intelligence chat model
Updated 5 months, 2 weeks ago
771.8K runs

openai/o4-miniOpenAI's fast, lightweight reasoning model
Updated 5 months, 2 weeks ago
471.9K runs

openai/o1OpenAI's first o-series reasoning model
Updated 5 months, 2 weeks ago
18.8K runs

openai/gpt-4.1OpenAI's Flagship GPT model for complex tasks.
Updated 5 months, 2 weeks ago
347.2K runs

openai/gpt-4.1-nanoFastest, most cost-effective GPT-4.1 model from OpenAI
Updated 5 months, 2 weeks ago
2.5M runs

openai/gpt-4.1-miniFast, affordable version of GPT-4.1
Updated 5 months, 2 weeks ago
2.8M runs

openai/gpt-5-structuredGPT-5 with support for structured outputs, web search and custom tools
Updated 5 months, 2 weeks ago
568.6K runs

openai/gpt-5OpenAI's new model excelling at coding, writing, and reasoning.
Updated 5 months, 2 weeks ago
2.3M runs

openai/gpt-5-nanoFastest, most cost-effective GPT-5 model from OpenAI
Updated 5 months, 2 weeks ago
14.6M runs

openai/gpt-5-miniFaster version of OpenAI's flagship GPT-5 model
Updated 5 months, 2 weeks ago
2.5M runs

openai/gpt-image-1.5OpenAI's latest image generation model with better instruction following and adherence to prompts
Updated 5 months, 2 weeks ago
14.1M runs

openai/gpt-image-1-miniA cost-efficient version of GPT Image 1
Updated 5 months, 2 weeks ago
637.7K runs

openai/sora-2-proOpenAI's Most advanced synced-audio video generation
Updated 5 months, 2 weeks ago
116.7K runs

openai/sora-2OpenAI's Flagship video generation with synced audio
Updated 5 months, 2 weeks ago
337.9K runs

4 step distilled version of FLUX.2 [klein]. A foundation model for maximum flexibility and control
Updated 5 months, 2 weeks ago
2.1M runs

An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering.
Updated 5 months, 2 weeks ago
1.9M runs
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video
Updated 5 months, 3 weeks ago
304.7K runs
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B image-to-video
Updated 5 months, 3 weeks ago
12.7M runs

Un-distilled version of FLUX.2 [klein]. A foundation model for maximum flexibility and control
Updated 5 months, 3 weeks ago
72.3K runs

Un-distilled version of FLUX.2 [klein]. Optimized for fine-tuning, customization, and post-training workflows
Updated 5 months, 3 weeks ago
60.5K runs

Very fast image generation and editing model. 4 steps distilled, sub-second inference for production and near real-time applications.
Updated 5 months, 3 weeks ago
23.9M runs

openai/dall-e-2The original classic DALLᐧE 2
Updated 6 months ago
2.6K runs

openai/dall-e-3An AI system that can create realistic images and art from a description in natural language.
Updated 6 months ago
248.3K runs
philz1337x/crystal-video-upscalerHigh-precision video upscaler optimized for portraits, faces and products. One of the upscale modes powered by Clarity AI. X:https://x.com/philz1337x
Updated 6 months ago
4.5K runs
lightricks/ltx-2-distilledLTX-2: The first open source audio-video model
Updated 6 months ago
27K runs
Kling 2.6 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation
Updated 6 months, 1 week ago
884.1K runs

Qwen Image 2512 is an improved version of Qwen Image with more realistic human generation, finer textures, and stronger text rendering
Updated 6 months, 1 week ago
149.3K runs
bytedance/seedance-1.5-proA joint audio-video model that accurately follows complex instructions.
Updated 6 months, 2 weeks ago
3.6M runs

An enhanced version over Qwen-Image-Edit-2509, featuring multiple improvements including notably better consistency
Updated 6 months, 2 weeks ago
4.1M runs
Alibaba Wan 2.6 text to video generation model
Updated 6 months, 3 weeks ago
16.9K runs
Alibaba Wan 2.6 image to video generation model
Updated 6 months, 3 weeks ago
46.7K runs

The fastest open source TTS model without sacrificing quality.
Updated 6 months, 3 weeks ago
523K runs

openai/gpt-5.2The best model for coding and agentic tasks across industries
Updated 6 months, 4 weeks ago
861.3K runs
Realistic lipsync with refined human emotion capabilities
Updated 6 months, 4 weeks ago
1.1K runs
Alibaba Wan 2.5 text to video generation model
Updated 7 months ago
36.6K runs
Alibaba Wan 2.5 Image to video generation with background audio
Updated 7 months ago
218.4K runs

Sound on: Google’s flagship Veo 3 text to video model, with audio
Updated 7 months, 2 weeks ago
235.5K runs

A faster and cheaper version of Google’s Veo 3 video model, with audio
Updated 7 months, 2 weeks ago
204.5K runs

State of the art video generation model. Veo 2 can faithfully follow simple and complex instructions, and convincingly simulates real-world physics as well as a wide range of visual styles.
Updated 7 months, 2 weeks ago
108.4K runs

Lyria 2 is a music generation model that produces 48kHz stereo audio through text-based prompts
Updated 7 months, 2 weeks ago
158.2K runs

Quality image generation and editing with support for reference images
Updated 7 months, 2 weeks ago
3.4M runs
lightricks/ltx-2-retakeTake any shot and edit specific sections. Rephrase, change the action, camera angles and more
Updated 7 months, 2 weeks ago
4.1K runs

Quickly generate smooth 5s or 8s videos at 540p, 720p or 1080p
Updated 7 months, 2 weeks ago
46K runs

Quickly make 5s or 8s videos at 540p, 720p or 1080p. It has enhanced motion, prompt coherence and handles complex actions well.
Updated 7 months, 2 weeks ago
267.8K runs

Create 5s-8s videos with enhanced character movement, visual effects, and exclusive 1080p-8s support. Optimized for anime characters and complex actions
Updated 7 months, 2 weeks ago
787.7K runs

Create videos in as little as 10 seconds. 5s or 8s videos at 360p, 540p, 720p or 1080p.
Updated 7 months, 2 weeks ago
3.3K runs
Generate realistic lipsync animations from audio for high-quality synchronization
Updated 7 months, 2 weeks ago
463.4K runs
Wan 2.5 text-to-video, optimized for speed
Updated 7 months, 2 weeks ago
51.4K runs

Accelerated inference for Wan 2.1 14B text to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
Updated 7 months, 2 weeks ago
37.4K runs

Accelerated inference for Wan 2.1 14B image to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
Updated 7 months, 2 weeks ago
89.7K runs

Accelerated inference for Wan 2.1 14B image to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
Updated 7 months, 2 weeks ago
455.4K runs

A 20B MMDiT model for next-gen text-to-image generation
Updated 7 months, 2 weeks ago
12.2K runs

bytedance/dreamina-3.14MP text-to-image generation with enhanced cinematic-quality image generation with precise style control, improved text rendering, and commercial design optimization.
Updated 7 months, 2 weeks ago
123.3K runs

philz1337x/crystal-upscalerHigh-precision image upscaler optimized for portraits, faces and products. One of the upscale modes powered by Clarity AI. X:https://x.com/philz1337x
Updated 7 months, 2 weeks ago
1M runs

bytedance/seedream-4Unified text-to-image generation and precise single-sentence editing at up to 4K resolution
Updated 7 months, 2 weeks ago
37.5M runs

Generate complex 3D models from images with Rodin Gen-2
Updated 7 months, 2 weeks ago
7.6K runs

All the tools you need for generating pixel art tilesets
Updated 7 months, 2 weeks ago
11.1K runs

High quality and authentic pixel art image generation
Updated 7 months, 2 weeks ago
34.9K runs

Fast pixel art image generation
Updated 7 months, 2 weeks ago
36.9K runs

Style consistent animated pixel art sprite generation
Updated 7 months, 2 weeks ago
12K runs
bytedance/omni-human-1.5A film-grade digital human model that generates realistic video from a single image, audio clip, and optional text prompt.
Updated 7 months, 3 weeks ago
45.4K runs

openai/gpt-5.1The best model for coding and agentic tasks with configurable reasoning effort.
Updated 7 months, 3 weeks ago
245.5K runs

Fusion – Product/object blending that fixes perspective and lighting so the subject melts into a new background via the Fusion LoRA.
Updated 7 months, 3 weeks ago
1.9K runs

Relight – Soft, curtain-filtered relighting that repaints the scene with golden-hour or moody tones using the Relight LoRA.
Updated 7 months, 3 weeks ago
4.2K runs

Upscale – Detail-loving upscale/restore pass that sharpens textures and color fidelity with the Upscale LoRA.
Updated 7 months, 3 weeks ago
2.2K runs

Next Scene – “Next beat” cinematic edits that keep subject identity while steering to the next camera move via the Next Scene LoRA
Updated 7 months, 3 weeks ago
5.2K runs

Skin – Natural beauty retouch that enhances pores and tonal variation (no plastic skin) via the Skin LoRA.
Updated 7 months, 3 weeks ago
14.7K runs

Photo to Anime – Stylized conversion that turns photos into crisp cel-shaded anime frames using the Photo-to-Anime LoRA.
Updated 7 months, 3 weeks ago
3.5K runs

Generate synced sounds for any video and return it with its new soundtrack - now enhanced in version 1.5 for improved sound synchronization and realism
Updated 7 months, 3 weeks ago
135.6K runs
Generate synced sounds for any video, and return it with its new sound track
Updated 7 months, 3 weeks ago
5.6K runs

an open-source, 2B-parameter model built for real-world applications
Updated 7 months, 3 weeks ago
45.7K runs

Qwen Image Edit 2509 LoRA explorer, uses HuggingFace URLs to load any safetensor
Updated 7 months, 3 weeks ago
509.4K runs

Image generation model from Reve
Updated 7 months, 3 weeks ago
108.3K runs

Image editing model from Reve
Updated 7 months, 3 weeks ago
100.4K runs

Image generation model from Reve which handles multiple input reference images
Updated 7 months, 3 weeks ago
42K runs

Reve's fast image edit model at only $0.01 per edit
Updated 7 months, 3 weeks ago
51.3K runs

An experimental FLUX Kontext model that can combine two input images
Updated 7 months, 3 weeks ago
246.2K runs

Become a character, in style
Updated 7 months, 3 weeks ago
101.4K runs

A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts
Updated 7 months, 3 weeks ago
12.3M runs

Quickly change someone's hair style and hair color, powered by FLUX.1 Kontext [pro]
Updated 7 months, 3 weeks ago
212.2K runs

Create a professional headshot photo from any single image
Updated 7 months, 3 weeks ago
81.8K runs

A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language
Updated 7 months, 3 weeks ago
52.4M runs

Use FLUX Kontext to restore, fix scratches and damage, and colorize old photos
Updated 7 months, 3 weeks ago
1.2M runs

Use flux-kontext-pro to change the first or last frame of a video. Useful to use as inputs for restyling an entire video in a certain way
Updated 7 months, 3 weeks ago
653 runs

Remove all text from an image with FLUX.1 Kontext
Updated 7 months, 3 weeks ago
142.1K runs

An experimental model with FLUX Kontext Pro that can combine two input images
Updated 7 months, 3 weeks ago
2.4M runs

Create a series of portrait photos from a single image
Updated 7 months, 3 weeks ago
90.1K runs

Bring your subjects into focus with FLUX.1 Kontext [pro]
Updated 7 months, 3 weeks ago
2.8K runs

Turn your image into a cartoon with FLUX.1 Kontext [pro]
Updated 7 months, 3 weeks ago
156.6K runs

Add simple filters to your images
Updated 7 months, 3 weeks ago
9K runs

FLUX Kontext max with list input for multiple images
Updated 7 months, 3 weeks ago
185.2K runs

Experience impossible adventures and extreme scenarios from a single image
Updated 7 months, 3 weeks ago
6.4K runs

Put yourself in an iconic location around the world from a single image
Updated 7 months, 3 weeks ago
19.9K runs

Camera-aware edits for Qwen/Qwen-Image-Edit-2509 with Lightning + multi-angle LoRA
Updated 7 months, 4 weeks ago
780.8K runs

Inference model for FLUX 1.1 [pro] Ultra using custom `finetune_id`. Supports 4MP images and raw mode for realism
Updated 7 months, 4 weeks ago
110.7K runs

Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.
Updated 7 months, 4 weeks ago
71.5M runs

Inference model for FLUX.1 [pro] using custom `finetune_id`
Updated 7 months, 4 weeks ago
10.9K runs

State-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.
Updated 7 months, 4 weeks ago
14.2M runs
bytedance/omni-humanTurns your audio/video/images into professional-quality animated videos
Updated 7 months, 4 weeks ago
161.3K runs

bytedance/seedance-1-proA pro version of Seedance that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 1080p resolution
Updated 7 months, 4 weeks ago
2.2M runs

bytedance/seedream-3A text-to-image model with support for native high-resolution (2K) image generation
Updated 7 months, 4 weeks ago
3.4M runs
bytedance/seedance-1-pro-fastA faster and cheaper version of Seedance 1 Pro
Updated 7 months, 4 weeks ago
1.7M runs

prunaai/flux-fastThis is the fastest Flux endpoint in the world.
Updated 8 months ago
42.1M runs

openai/gpt-4o-mini-transcribeA speech-to-text model that uses GPT-4o mini to transcribe audio
Updated 8 months ago
23.6K runs
Generate 5s and 10s videos in 720p resolution at 30fps
Updated 8 months ago
1.8K runs

openai/gpt-4o-transcribeA speech-to-text model that uses GPT-4o to transcribe audio
Updated 8 months ago
63.8K runs

Create 5s 480p videos from a text prompt
Updated 8 months ago
11.8K runs

Generate 5s and 10s videos in 720p resolution
Updated 8 months ago
107.7K runs

Leonardo AI’s first foundational model produces images up to 5 megapixels (fast, quality and ultra modes)
Updated 8 months ago
39.6K runs

Artistic and high-quality visuals with improved prompt adherence, diversity, and definition
Updated 8 months ago
280.8K runs

recraft-ai/recraft-20b-svgAffordable and fast vector images
Updated 8 months ago
127.4K runs

recraft-ai/recraft-v3Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis
Updated 8 months ago
8.5M runs

recraft-ai/recraft-v3-svgRecraft V3 SVG (code-named red_panda) is a text-to-image model with the ability to generate high quality SVG images including logotypes, and icons. The model supports a wide list of styles.
Updated 8 months ago
437.8K runs

recraft-ai/recraft-20bAffordable and fast images
Updated 8 months ago
335.3K runs
Generate realistic lipsyncs with Sync Labs' 2.0 model
Updated 8 months ago
40.2K runs

Generate 5s and 10s videos in 1080p resolution
Updated 8 months ago
841.3K runs

A premium version of Kling v2.1 with superb dynamics and prompt adherence. Generate 1080p 5s and 10s videos from text or an image
Updated 8 months ago
107.8K runs

ideogram-ai/ideogram-v3-turboTurbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles
Updated 8 months ago
9.3M runs
Generate 5s and 10s videos in 1080p resolution at 30fps
Updated 8 months ago
4K runs

Generate 5s and 10s videos in 720p resolution at 30fps
Updated 8 months ago
1.7M runs

ideogram-ai/ideogram-v2a-turboLike Ideogram v2 turbo, but now faster and cheaper
Updated 8 months ago
391.4K runs

ideogram-ai/ideogram-characterGenerate consistent characters from a single reference image. Outputs can be in many styles. You can also use inpainting to add your character to an existing image.
Updated 8 months ago
588.5K runs
Add lip-sync to any video with an audio file or text
Updated 8 months ago
50.8K runs

Use Kling v2.1 to generate 5s and 10s videos in 720p and 1080p resolution from a starting image (image-to-video)
Updated 8 months ago
4.1M runs

ideogram-ai/ideogram-v2An excellent image model with state of the art inpainting, prompt comprehension and text rendering
Updated 8 months ago
2.9M runs

ideogram-ai/ideogram-v3-qualityThe highest quality Ideogram v3 model. v3 creates images with stunning realism, creative designs, and consistent styles
Updated 8 months ago
2.3M runs

ideogram-ai/ideogram-v2aLike Ideogram v2, but faster and cheaper
Updated 8 months ago
2.1M runs

ideogram-ai/ideogram-v3-balancedBalance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles
Updated 8 months ago
486.9K runs

ideogram-ai/ideogram-v2-turboA fast image model with state of the art inpainting, prompt comprehension and text rendering.
Updated 8 months ago
2.9M runs

luma/modify-videoModify a video with style transfer and prompt-based editing
Updated 8 months ago
11.9K runs

luma/ray-2-540pGenerate 5s and 9s 540p videos
Updated 8 months ago
12K runs

luma/ray-2-720pGenerate 5s and 9s 720p videos
Updated 8 months ago
43.9K runs
Wan 2.5 image-to-video, optimized for speed
Updated 8 months ago
75.7K runs

Accelerated inference for Wan 2.1 14B text to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
Updated 8 months ago
194.5K runs

stability-ai/stable-diffusion-3.5-medium2.5 billion parameter image model with improved MMDiT-X architecture
Updated 8 months ago
121.2K runs

luma/reframe-videoChange the aspect ratio of any video up to 30 seconds long, outputs will be 720p
Updated 8 months ago
65K runs

luma/ray-flash-2-720pGenerate 5s and 9s 720p videos, faster and cheaper than Ray 2
Updated 8 months ago
82.3K runs

stability-ai/stable-diffusion-3.5-largeA text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, thanks to Query-Key Normalization.
Updated 8 months ago
2.1M runs

stability-ai/stable-diffusion-3.5-large-turboA text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, with a focus on fewer inference steps
Updated 8 months ago
1.1M runs

runwayml/gen4-image-turboGen-4 Image Turbo is cheaper and 2.5x faster than Gen-4 Image. An image model with references, use up to 3 reference images to create the exact image you need. Capture every angle.
Updated 8 months ago
122.2K runs

Generate 6s videos with prompts or images. (Also known as Hailuo). Use a subject reference to make a video with a character and the S2V-01 model.
Updated 8 months ago
732.3K runs

Generate videos with specific camera movements
Updated 8 months ago
77.2K runs
A high-fidelity video generation model optimized for realistic human motion, cinematic VFX, expressive characters, and strong prompt and style adherence across both text-to-video and image-to-video workflows
Updated 8 months ago
104.5K runs
A lower-latency image-to-video version of Hailuo 2.3 that preserves core motion quality, visual consistency, and stylization performance while enabling faster iteration cycles.
Updated 8 months ago
221.6K runs

An image-to-video (I2V) model specifically trained for Live2D and general animation use cases
Updated 8 months ago
189.3K runs

runwayml/gen4-imageRunway's Gen-4 Image model with references. Use up to 3 reference images to create the exact image you need. Capture every angle.
Updated 8 months ago
1.2M runs
runwayml/gen4-alephA new way to edit, transform and generate video
Updated 8 months ago
269.2K runs

Clone voices to use with Minimax's speech-02-hd and speech-02-turbo
Updated 8 months ago
71.5K runs
runwayml/gen4-turboGenerate 5s and 10s 720p videos fast
Updated 8 months ago
111.5K runs
luma/ray-flash-2-540pGenerate 5s and 9s 540p videos, faster and cheaper than Ray 2
Updated 8 months ago
77.7K runs
Hailuo 2 is a text-to-video and image-to-video model that can make 6s or 10s videos at 768p (standard) or 1080p (pro). It excels at real world physics.
Updated 8 months ago
429.6K runs

Music-1.5: Full-length songs (up to 4 mins) with natural vocals & rich instrumentation
Updated 8 months ago
94.3K runs

Minimax's first image model, with character reference support
Updated 8 months ago
3.1M runs
A low cost and fast version of Hailuo 02. Generate 6s and 10s videos in 512p
Updated 8 months ago
55.7K runs

Quickly generate up to 1 minute of music with lyrics and vocals in the style of a reference track
Updated 8 months ago
547.9K runs

luma/photon-flashAccelerated variant of Photon prioritizing speed while maintaining quality
Updated 8 months ago
559.4K runs

stability-ai/stable-audio-2.5Generate high-quality music and sound from text prompts
Updated 8 months ago
74.3K runs

prunaai/flux-kontext-fastUltra fast flux kontext endpoint
Updated 8 months ago
23M runs

Professional edge-guided image generation. Control structure and composition using Canny edge detection
Updated 8 months, 1 week ago
442.7K runs

Professional depth-aware image generation. Edit images while preserving spatial relationships.
Updated 8 months, 1 week ago
335.2K runs

Compose a song from a prompt or a composition plan
Updated 8 months, 1 week ago
94.2K runs

Fine-tunable Qwen Image model with exceptional composition abilities - train custom LoRAs for any style or subject
Updated 8 months, 1 week ago
1.3K runs

nightmareai/real-esrganReal-ESRGAN with optional face correction and adjustable upscale
Updated 8 months, 1 week ago
94.2M runs

High quality, low latency text to speech in 32 languages
Updated 8 months, 2 weeks ago
51.9K runs

Generate multilingual text-to-speech audio in over 30 languages
Updated 8 months, 2 weeks ago
18.6K runs

ElevenLabs's fastest speech synthesis model
Updated 8 months, 2 weeks ago
71.4K runs

The most expressive Text to Speech model
Updated 8 months, 2 weeks ago
68.5K runs

Convert PDF to markdown + JSON quickly with high accuracy
Updated 8 months, 2 weeks ago
65.8K runs

Detect and transcribe text in images with accurate bounding boxes, layout analysis, reding order, and table recognition, in 90 languages
Updated 8 months, 2 weeks ago
205.8K runs

Claude Haiku 4.5 gives you similar levels of coding performance but at one-third the cost and more than twice the speed
Updated 8 months, 3 weeks ago
1.6M runs

tencent/hunyuan-image-3A powerful native multimodal model for image generation (PrunaAI squeezed)
Updated 9 months ago
85.2K runs

openai/gpt-5-proThe smartest, fastest, most useful model yet, with built-in thinking that puts expert-level intelligence in everyone’s hands
Updated 9 months ago
4.8K runs
Ovi: generate videos with audio from image and text inputs
Updated 9 months ago
14.5K runs

Claude Sonnet 4.5 is the best coding model to date, with significant improvements across the entire development lifecycle
Updated 9 months, 1 week ago
1.6M runs
Use Wan 2.2 Animate to copy the motion of a video to another scene
Updated 9 months, 2 weeks ago
28.2K runs

The latest Qwen-Image’s iteration with improved multi-image editing, single-image consistency, and native support for ControlNet
Updated 9 months, 2 weeks ago
11.3M runs

openai/gpt-image-1A multimodal image generation model that creates high-quality images. You need to bring your own verified OpenAI key to use this model. Your OpenAI account will be charged for usage.
Updated 9 months, 2 weeks ago
1.8M runs

ibm-granite/granite-3.3-8b-instructGranite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities.
Updated 9 months, 2 weeks ago
1.7M runs

Updated 9 months, 3 weeks ago
608 runs

tencent/hunyuan-image-2.1Generate high-quality 2K resolution images from text prompts
Updated 9 months, 3 weeks ago
21.9K runs
Generate a video from an audio clip and a reference image
Updated 9 months, 3 weeks ago
123.3K runs

Add consistent, customizable shadows to product cutouts for enhanced visual appeal
Updated 9 months, 4 weeks ago
4K runs

Transform any product photo into professional 2000x2000px packshots with optimal positioning
Updated 9 months, 4 weeks ago
1.6K runs

Precise AI-powered product cutout with 256-level transparency for eCommerce
Updated 9 months, 4 weeks ago
1.7K runs

Edit images using a prompt. This model extends Qwen-Image’s unique text rendering capabilities to image editing tasks, enabling precise text editing
Updated 10 months, 3 weeks ago
2M runs

fofr/color-matcherColor match and white balance fixes for images
Updated 10 months, 3 weeks ago
229.9K runs

openai/o1-miniA small model alternative to o1
Updated 10 months, 3 weeks ago
3.4K runs

openai/gpt-4o-miniLow latency, low cost version of OpenAI's GPT-4o model
Updated 10 months, 3 weeks ago
39.9M runs

Image-to-video at 720p and 480p with Wan 2.2 A14B
Updated 11 months ago
57.7K runs
The fastest Wan 2.2 text-to-image and image-to-video model
Updated 11 months ago
763.1K runs

openai/clipOfficial CLIP models, generate CLIP (clip-vit-large-patch14) text & image embeddings
Updated 11 months, 1 week ago
7.6M runs

An opinionated text-to-image model from Black Forest Labs in collaboration with Krea that excels in photorealism. Creates images that avoid the oversaturated "AI look".
Updated 11 months, 1 week ago
3M runs

ibm-granite/granite-speech-3.3-8bGranite-speech-3.3-8b is a compact and efficient speech-language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST).
Updated 11 months, 1 week ago
20.6K runs

ibm-granite/granite-vision-3.3-2bGranite-vision-3.3-2b is a compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
Updated 11 months, 1 week ago
263.2K runs

FLUX.1 Kontext[dev] image editing model for running lora finetunes
Updated 11 months, 2 weeks ago
282.5K runs

prunaai/wan-2.2-imageThis model generates beautiful cinematic 2 megapixel images in 3-4 seconds and is derived from the Wan 2.2 model through optimisation techniques from the pruna package
Updated 11 months, 3 weeks ago
1.2M runs

Open-weight version of FLUX.1 Kontext
Updated 1 year ago
7.9M runs

A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference
Updated 1 year ago
6M runs

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions
Updated 1 year ago
50.2M runs

The fastest image generation model tailored for local development and personal use
Updated 1 year ago
682.7M runs

The fastest image generation model tailored for fine-tuned use
Updated 1 year ago
3.7M runs

Generate expressive, natural speech. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.
Updated 1 year ago
394.7K runs

Generate expressive, natural speech with Resemble AI's Chatterbox.
Updated 1 year ago
19.4K runs

Claude Sonnet 4 is a significant upgrade to 3.7, delivering superior coding and reasoning while responding more precisely to your instructions
Updated 1 year ago
3.1M runs

ibm-granite/granite-embedding-278m-multilingualGranite-Embedding-278M-Multilingual is a 278M parameter model from the Granite Embeddings suite that can be used to generate high quality text embeddings
Updated 1 year, 1 month ago
4.5K runs

Use one or two face images to create AI avatars
Updated 1 year, 2 months ago
37.4K runs

topazlabs/image-upscaleProfessional-grade image upscaling, from Topaz Labs
Updated 1 year, 2 months ago
3M runs

topazlabs/video-upscaleVideo Upscaling from Topaz Labs
Updated 1 year, 2 months ago
958.5K runs

Open-weight inpainting model for editing and extending images. Guidance-distilled from FLUX.1 Fill [pro].
Updated 1 year, 3 months ago
1.9M runs

Fast, efficient image variation model for rapid iteration and experimentation.
Updated 1 year, 3 months ago
75.8K runs

Open-weight image variation model. Create new versions while preserving key elements of your original.
Updated 1 year, 3 months ago
344K runs

Open-weight depth-aware image generation. Edit images while preserving spatial relationships.
Updated 1 year, 3 months ago
1.3M runs

Open-weight edge-guided image generation. Control structure and composition using Canny edge detection.
Updated 1 year, 3 months ago
247.7K runs

ibm-granite/granite-3.2-8b-instructGranite-3.2-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for reasoning and instruction-following capabilities.
Updated 1 year, 4 months ago
460.5K runs

Generate 5s 480p videos. Wan is an advanced and powerful visual generation model developed by Tongyi Lab of Alibaba Group
Updated 1 year, 4 months ago
50.2K runs

The most intelligent Claude model and the first hybrid reasoning model on the market (claude-3-7-sonnet-20250219)
Updated 1 year, 4 months ago
4.2M runs

Anthropic's fastest, most cost-effective model, with a 200K token context window (claude-3-5-haiku-20241022)
Updated 1 year, 4 months ago
3.1M runs

playht/play-dialogEnd-to-end AI speech model designed for natural-sounding conversational speech synthesis, with support for context-aware prosody, intonation, and emotional expression.
Updated 1 year, 5 months ago
27.1K runs

ibm-granite/granite-3.1-8b-instructGranite-3.1-8B-Instruct is a lightweight and open-source 8B parameter model is designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.
Updated 1 year, 6 months ago
778.1K runs

ibm-granite/granite-3.1-2b-instructGranite-3.1-2B-Instruct is a lightweight and open-source 2B parameter model designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.
Updated 1 year, 6 months ago
9.2K runs

luma/photonHigh-quality image generation model optimized for creative professional workflows and ultra-high fidelity outputs
Updated 1 year, 7 months ago
3.3M runs

ibm-granite/granite-3.0-8b-instructGranite-3.0-8B-Instruct is a lightweight and open-source 8B parameter model is designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.
Updated 1 year, 8 months ago
181.4K runs

ibm-granite/granite-3.0-2b-instructGranite-3.0-2B-Instruct is a lightweight and open-source 2B parameter model designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.
Updated 1 year, 8 months ago
420.3K runs

ibm-granite/granite-8b-code-instruct-128kJoin the Granite community where you can find numerous recipe workbooks to help you get started with a wide variety of use cases using this model. https://github.com/ibm-granite-community
Updated 1 year, 10 months ago
556.2K runs

ibm-granite/granite-20b-code-instruct-8kJoin the Granite community where you can find numerous recipe workbooks to help you get started with a wide variety of use cases using this model. https://github.com/ibm-granite-community
Updated 1 year, 10 months ago
110K runs

stability-ai/stable-diffusion-3A text-to-image model with greatly improved performance in image quality, typography, complex prompt understanding, and resource-efficiency
Updated 1 year, 11 months ago
1.9M runs

snowflake/snowflake-arctic-instructAn efficient, intelligent, and truly open-source language model
Updated 2 years, 2 months ago
2M runs

meta/meta-llama-3-70bBase version of Llama 3, a 70 billion parameter language model from Meta.
Updated 2 years, 2 months ago
872.4K runs

meta/meta-llama-3-70b-instructA 70 billion parameter language model from Meta, fine tuned for chat completions
Updated 2 years, 2 months ago
169.8M runs

meta/meta-llama-3-8b-instructAn 8 billion parameter language model from Meta, fine tuned for chat completions
Updated 2 years, 2 months ago
416.6M runs

meta/meta-llama-3-8bBase version of Llama 3, an 8 billion parameter language model from Meta.
Updated 2 years, 2 months ago
51.4M runs

falcons-ai/nsfw_image_detectionFine-Tuned Vision Transformer (ViT) for NSFW Image Classification
Updated 2 years, 7 months ago
126.8M runs

meta/llama-2-7b-chatA 7 billion parameter language model from Meta, fine tuned for chat completions
Updated 2 years, 8 months ago
18.6M runs

mistralai/mistral-7b-v0.1A 7 billion parameter language model from Mistral.
Updated 2 years, 9 months ago
1.9M runs

meta/llama-2-70b-chatA 70 billion parameter language model from Meta, fine tuned for chat completions
Updated 2 years, 9 months ago
10.1M runs

meta/llama-2-70bBase version of Llama 2, a 70 billion parameter language model from Meta.
Updated 2 years, 9 months ago
471.8K runs

meta/llama-2-13b-chatA 13 billion parameter language model from Meta, fine tuned for chat completions
Updated 2 years, 9 months ago
4.9M runs

meta/llama-2-13bBase version of Llama 2 13B, a 13 billion parameter language model
Updated 2 years, 9 months ago
209.4K runs

meta/llama-2-7bBase version of Llama 2 7B, a 7 billion parameter language model
Updated 2 years, 9 months ago
659.8K runs